124 Hits in 3.7 sec

A machine learning-based service for estimating quality of genomes using PATRIC

Bruce Parrello, Rory Butler, Philippe Chlenski, Robert Olson, Jamie Overbeek, Gordon D. Pusch, Veronika Vonstein, Ross Overbeek
2019 BMC Bioinformatics  
We have added two quality assessment tools to the PATRIC annotation pipeline. EvalCon uses supervised machine learning to calculate an annotation consistency score.  ...  Additionally, we provide contamination, completeness, and consistency measures for all genomes in PATRIC and in a recent set of metagenomic assemblies.  ...  Acknowledgments We thank Ralph Butler for his contributions to this paper.  ... 
doi:10.1186/s12859-019-3068-y pmid:31581946 pmcid:PMC6775668 fatcat:ertmvmsb4nbpfkar6qyt6w4gva

The PATRIC Bioinformatics Resource Center: expanding data and analysis capabilities

2019 Nucleic Acids Research  
Here we report the recent updates to the PATRIC resource, including new web-based comparative analysis tools, eight new services and the release of a command-line interface to access, query and analyze  ...  PATRIC offers web-based visualization and comparative analysis tools, a private workspace in which users can analyze their own data in the context of the public collections, services that streamline complex  ...  These collections of structured metadata provide the foundation for running machine learning and deep learning experiments (10, 11) , and for providing predictive tools to users (9) .  ... 
doi:10.1093/nar/gkz943 pmid:31667520 pmcid:PMC7145515 fatcat:jmpq54pzkvhcfaxjzr25f2ypri

Identifying Genomic Islands with Deep Neural Networks [article]

Rida Assaf, Fangfang Xia, Rick Stevens
2019 bioRxiv   pre-print
We propose a method, which we call Shutter Island, that uses a deep learning model widely used in computer vision (Inception V3), to detect Genomic Islands.  ...  The intrinsic value of machine learning methods lies in their ability to generalize.  ...  One of the services PATRIC provides is the compare region viewer service, where a query genome is aligned against a set of other related genomes anchored at a specific focus gene/peg.  ... 
doi:10.1101/525030 fatcat:tfadoj2jnnfk5ihrkwbdnc5fl4

AMR-meta: a k-mer and metafeature approach to classify antimicrobial resistance from high-throughput short-read metagenomics data

Simone Marini, Marco Oliva, Ilya B Slizovskiy, Rishabh A Das, Noelle Robertson Noyes, Tamer Kahveci, Christina Boucher, Mattia Prosperi
2022 GigaScience  
Results We present AMR-meta, a database-free and alignment-free approach, based on k-mers, which combines algebraic matrix factorization into metafeatures with regularized regression.  ...  In addition, AMR-meta uses an augmented training strategy that joins an AMR gene database with non-AMR genes (used as negative examples).  ...  Another class of methods for AMR characterization is alignment-free, using a variety of approaches including substring (k-mer) matching and machine learning.  ... 
doi:10.1093/gigascience/giac029 pmid:35583675 pmcid:PMC9116207 fatcat:qt74dkf3ebgabeyj6y7extnib4

Machine Learning Approaches for Epidemiological Investigations of Food-Borne Disease Outbreaks

Baiba Vilne, Irēna Meistere, Lelde Grantiņa-Ieviņa, Juris Ķibilds
2019 Frontiers in Microbiology  
As genotyping using whole-genome sequencing (WGS) is becoming more accessible and affordable, it is increasingly used as a routine tool for the detection of pathogens, and has the potential to differentiate  ...  In each step, ML could be used to increase the speed and potentially the accuracy (provided increasing amounts of high-quality input data) of identification of the source of ongoing outbreaks, leading  ...  When a genome is submitted to the PATRIC annotation service, these classifiers are used to predict if the organism is susceptible or resistant to an antibiotic.  ... 
doi:10.3389/fmicb.2019.01722 pmid:31447800 pmcid:PMC6691741 fatcat:3kuz7hgocrepjemyb5gb7mg7my

Predicting the pathogenicity of bacterial genomes using widely spread protein families

Shaked Naor-Hoffmann, Dina Svetlitsky, Neta Sal-Man, Yaron Orenstein, Michal Ziv-Ukelson
2022 BMC Bioinformatics  
Results We developed a wide scope pathogenicity classifier (WSPC), a new protein-content-based machine-learning classification model.  ...  Previous methods for classification of bacteria as pathogenic or non-pathogenic used either raw genomic reads or protein families as features.  ...  The PATRIC database provides PGFam annotations for the genes of each bacterial genome in it, and an annotation service for a new genome uploaded by the user.  ... 
doi:10.1186/s12859-022-04777-w pmid:35751023 pmcid:PMC9233384 fatcat:fmmqgdso5raq5kmqd3lbhix54u

Genomics of antibiotic-resistance prediction in Pseudomonas aeruginosa

Julie Jeukens, Luca Freschi, Irena Kukavica-Ibrulj, Jean-Guillaume Emond-Rheault, Nicholas P. Tucker, Roger C. Levesque
2017 Annals of the New York Academy of Sciences  
We now have the capability to sequence hundreds of bacterial genomes per week, including assembly and annotation.  ...  We review novel approaches for genotype prediction of antibiotic resistance.  ...  A special thanks to Andrew McArthur for his support and encouragement in using the Comprehensive Antibiotic Resistance Database. J.  ... 
doi:10.1111/nyas.13358 pmid:28574575 fatcat:szh4oh4aqvb7flfxjrlwdoizqq

Named Entity Recognition for Bacterial Type IV Secretion Systems

Sophia Ananiadou, Dan Sullivan, William Black, Gina-Anne Levow, Joseph J. Gillespie, Chunhong Mao, Sampo Pyysalo, BalaKrishna Kolluru, Junichi Tsujii, Bruno Sobral, Alan Ruttenberg
2011 PLoS ONE  
Based on an annotated corpus, large domain terminological resources, and machine learning techniques, we developed recognizers for these entities.  ...  In bacterial Type IV secretion systems genes within one set of orthologs may have over a dozen different names.  ...  Acknowledgments We would like to thank Lisa Gunderman (PATRIC) and Paul Thompson (NaCTeM) for help in preparing the manuscript. Author Contributions  ... 
doi:10.1371/journal.pone.0014780 pmid:21468321 pmcid:PMC3066171 fatcat:vahe7e6a6nd3vkik6enkk2owai

BacDive in 2022: the knowledge base for standardized bacterial and archaeal data

Lorenz Christian Reimer, Joaquim Sardà Carbasse, Julia Koblitz, Christian Ebeling, Adam Podstawka, Jörg Overmann
2021 Nucleic Acids Research  
Thereby bacterial strains can be systematically searched based on combinations of their attributes, e.g. growth and metabolic features for biotechnological applications or to identify gaps in the present  ...  By integrating high-quality data from additional culture collections as well as detailed information from species descriptions, the amount of data provided has increased by 30% over the past three years  ...  Moore and Manfred Rohde for providing comprehensive data and images. We like to thank CCUG, CABI and HZI for the friendly permission of data publishing. FUNDING  ... 
doi:10.1093/nar/gkab961 pmid:34718743 pmcid:PMC8728306 fatcat:ooc6w2zvwvfu3pyyo4xgemjmay

A Practical Approach for Predicting Antimicrobial Phenotype Resistance in Staphylococcus aureus Through Machine Learning Analysis of Genome Data

Shuyi Wang, Chunjiang Zhao, Yuyao Yin, Fengning Chen, Hongbin Chen, Hui Wang
2022 Frontiers in Microbiology  
Here, we firstly predicted the minimum inhibitory concentrations of ten antimicrobial agents for Staphylococcus aureus using 466 isolates by directly extracting k-mer from whole genome sequencing data  ...  combined with three machine learning algorithms: random forest, support vector machine, and XGBoost.  ...  All the authors approved the final version of the manuscript.  ... 
doi:10.3389/fmicb.2022.841289 pmid:35308374 pmcid:PMC8924536 fatcat:62ynftxtcrdzhiniut63tqnk7q

Key Questions for Next-Generation Biomonitoring

Andreas Makiola, Zacchaeus G. Compson, Donald J. Baird, Matthew A. Barnes, Sam P. Boerlijst, Agnès Bouchez, Georgina Brennan, Alex Bush, Elsa Canard, Tristan Cordier, Simon Creer, R. Allen Curry (+33 others)
2020 Frontiers in Environmental Science  
Next-generation biomonitoring (NGB) describes a suite of tools and approaches that allow the examination of a broader spectrum of organizational levels-from genes to entire ecosystems.  ...  Questions for Next-Generation Biomonitoring not exhaustive, this list covers most of the key challenges facing NGB, and provides the basis of the next steps for research and implementation in this field  ...  DAB, AM, SR, and CV would like to acknowledge the support of the Consortium Biocontrole, which provides funding for the BCMicrobiome project.  ... 
doi:10.3389/fenvs.2019.00197 fatcat:garu26qrbzgbldzsc5n6fi2avy

Genomic Investigation into the Virulome, Pathogenicity, Stress Response Factors, Clonal Lineages, and Phylogenetic Relationship of Escherichia coli Strains Isolated from Meat Sources in Ghana

Frederick Adzitey, Jonathan Asante, Hezekiel M Kumalo, Rene B Khan, Anou M Somboro, Daniel G Amoako
2020 Genes  
Estimation of pathogenicity predicted a higher average probability score (Pscore ≈ 0.937), supporting their pathogenic potential to humans.  ...  This study investigated the virulome, pathogenicity, stress response factors, clonal lineages, and the phylogenomic relationship of E. coli isolated from different meat sources in Ghana using whole-genome  ...  Acknowledgments: The authors are grateful to the University for Development Studies for making available a microbiology laboratory for this work.  ... 
doi:10.3390/genes11121504 pmid:33327465 pmcid:PMC7764966 fatcat:6llmye4epfh6zovnpdebzg7jq4

Pathogenomic Analysis of a Novel Extensively Drug-Resistant Citrobacter freundii Isolate Carrying a blaNDM-1 Carbapenemase in South Africa

Ramsamy, Mlisana, Amoako, Allam, Ismail, Singh, Abia, Essack
2020 Pathogens  
This study presents the background genomic information for future surveillance and tracking of the spread of carbapenem-resistant Enterobacteriaceae in South Africa.  ...  The estimated pathogenic potential predicted a higher probability (Pscore ≈ 0.875), supporting H2730R as a human pathogen.  ...  The pathogenic potential (P score ) is a machine learning algorithm used for the in silico prediction of the possibility of a strain being a human pathogen with the probability ranging from 0 to 1.  ... 
doi:10.3390/pathogens9020089 pmid:32024012 pmcid:PMC7168644 fatcat:s2vlex5pwjf5tcrbbbkcm7rhqq

Population Genomic Analysis of 1,777 Extended-Spectrum Beta-Lactamase-Producing Klebsiella pneumoniae Isolates, Houston, Texas: Unexpected Abundance of Clonal Group 307

S. Wesley Long, Randall J. Olsen, Todd N. Eagar, Stephen B. Beres, Picheng Zhao, James J. Davis, Thomas Brettin, Fangfang Xia, James M. Musser, Steven J. Projan
2017 mBio  
Using a comprehensive population-based sample of extended-spectrum beta-lactamase (ESBL)-producing K. pneumoniae strains, we show that a relatively uncommon clonal type, CG307, caused the plurality of  ...  We exploited the large data set to develop whole-genome sequence-based classifiers that accurately predict clinical antimicrobial resistance for 12 of the 16 antibiotics tested.  ...  Service (contract HHSN272201400027C).  ... 
doi:10.1128/mbio.00489-17 pmid:28512093 pmcid:PMC5433097 fatcat:c44oszbejneaxcfm63dbnmczua

SPS Members Recognized as Fellows and with Awards [Society News]

2012 IEEE Signal Processing Magazine  
Edward Dougherty, College Station, Texas: For contributions to the development of genomic signal processing. Gerard Dreyfus, Paris, France: For contributions to machine learning and its applications.  ...  Eligibility is based on a five-year window preceding the year of election, and judging is based on general quality, originality, subject matter, and timeliness.  ... 
doi:10.1109/msp.2012.943705 fatcat:x2b6fbnt65hede67ulnrxd3jhi
« Previous Showing results 1 — 15 out of 124 results